© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 86847
    Prev
    Next
    INDEX
    Explanations

    technical descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     on
    -1.91
     my
    -1.61
     because
    -1.48
     what
    -1.44
     than
    -1.41
     by
    -1.41
     other
    -1.30
     includes
    -1.30
     involves
    -1.25
     involving
    -1.25
    POSITIVE LOGITS
    already
    1.55
     últimos
    1.48
     último
    1.44
     самы
    1.41
    THERE
    1.38
    Already
    1.37
     of
    1.36
     azonban
    1.36
     Perſ
    1.35
     Deze
    1.30
    Activations Density 0.110%

    No Known Activations